Calculators wont give you completely wrong results, not even once, where "AI" does that way too often. If calculators did too, mathemeticians simply would not use them.
This is why using LLMs to generate deterministic code (with human-verified tests) is a much better idea than including LLMs directly in runtime systems.
Calculators wont give you completely wrong results, not even once, where "AI" does that way too often. If calculators did too, mathemeticians simply would not use them.
Most specifically, random wrong results. Some calculators have issues with rounding, but if you understand those issues, it's consistent.
Imagine driving your car, you turn right, but today turning right slams on the brakes, and 10 people rear end you! That's current AI.
This is why using LLMs to generate deterministic code (with human-verified tests) is a much better idea than including LLMs directly in runtime systems.
Yes in terms of raw LLM, but with some tools or a MCP the “AI” will never be wrong.
Including browsers with built-in “AI” & MCP draining user’s bank accounts.
https://news.ycombinator.com/item?id=45004846
That is not true at all.